Similarity Caching: Theory and Algorithms

TL;DR

This paper provides a comprehensive analysis of similarity caching systems, addressing their challenges and proposing new algorithms with guarantees, supported by evaluations on synthetic and real data.

Contribution

It introduces the first dynamic policies for similarity caching with some optimality guarantees, filling a gap in understanding and managing such systems.

Findings

Proposed the first dynamic policies with optimality guarantees

Analyzed similarity caching in various settings (offline, adversarial, stochastic)

Validated performance on synthetic and real request traces

Abstract

This paper focuses on similarity caching systems, in which a user request for an {object~$o$} that is not in the cache can be (partially) satisfied by a similar stored {object~$o'$}, at the cost of a loss of user utility. Similarity caching systems can be effectively employed in several application areas, like multimedia retrieval, recommender systems, genome study, and machine learning training/serving. However, despite their relevance, the behavior of such systems is far from being well understood. In this paper, we provide a first comprehensive analysis of similarity caching in the offline, adversarial, and stochastic settings. We show that similarity caching raises significant new challenges, for which we propose the first dynamic policies with some optimality guarantees. We evaluate the performance of our schemes under both synthetic and real request traces.